Harbor
Summary
Harbor is a CLI and companion tool for spinning up complete local LLM stacks.
Similar Articles
Harbor v0.4.19 - vllm/sglang/llama.cpp launch codex/claude/pi/opencode
Harbor v0.4.19 adds the ability to launch local agentic coding tools with local inference backends, integrating vllm, sglang, and llama.cpp, and includes a built-in LLM gateway for tool injection like web search.
WebHarbor - We "dock" the real websites into local for web agents! [R]
WebHarbor packages 15 real websites (Amazon, GitHub, BBC, etc.) as self-contained Flask+SQLite apps in a single Docker image with sub-second reset, designed for reproducible web agent evaluation and training. The project invites community contributions to expand to 100+ sites, with co-authorship opportunities.
ModelHub
ModelHub is a menu bar app for running local LLMs on Mac.
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
SafeHarbor is a novel framework for LLM agent safety that uses hierarchical memory and self-evolution to balance safety and utility, achieving state-of-the-art performance on benign and malicious tasks.
Show HN: Lathe – Use LLMs to learn a new domain, not skip past it
Lathe is an open-source tool that generates hands-on, multi-part technical tutorials from any prompt using LLMs, aiming to teach users rather than just provide answers. It includes a local UI for working through tutorials and supports integration with Claude Code, Cursor, and Codex.